single-cell-foundation-model-stofm

Community

Turn spatial data into actionable embeddings.

AuthorPharMolix
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill helps preprocess spatial transcriptomics data for the SToFM workflow, producing the input artifacts and embeddings needed for downstream region segmentation and cell type annotation.

Core Features & Use Cases

  • Preprocessing: convert raw spatial transcriptomics data into the SToFM-ready formats (hf.dataset and data.h5ad).
  • Embedding Generation: run the official cell encoder and SE(2) Transformer to produce cell embeddings for spatial graphs.
  • Downstream Tasks: support region segmentation and cell type annotation using the generated embeddings.
  • Local Repositories: tailored for a local SToFM repo at /DATA/disk0/zhaosy/home/SToFM.

Quick Start

Provide the local SToFM repository path and invoke the official preprocessing and embedding pipelines to generate the ready inputs and embeddings.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: single-cell-foundation-model-stofm
Download link: https://github.com/PharMolix/OpenBioMed/archive/main.zip#single-cell-foundation-model-stofm

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.